Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1910
    Prev
    Next
    INDEX
    Explanations

    specific references to genetic testing and evaluations related to populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.66
    Билгалдахарш
    -0.65
    IsMutable
    -0.62
    prüche
    -0.61
    ={`${
    -0.61
    textAppearance
    -0.60
     Spisak
    -0.60
    Bibliograf
    -0.57
     насељу
    -0.56
     '\\;'
    -0.54
    POSITIVE LOGITS
    GOTREF
    0.65
    wikk
    0.50
    fta
    0.49
    titem
    0.46
    iligung
    0.43
     SqlParameter
    0.42
    ruptedException
    0.42
     muualla
    0.41
    fect
    0.40
    IRQn
    0.40
    Activations Density 1.578%

    No Known Activations